Cost-effective wireless system for image-based microalgae biomass estimation with adaptive background correction

Accurate microalgae biomass estimation is essential for image-based cultivation monitoring, yet conventional RGB-based approaches remain sensitive to background chromaticity variations under different imaging conditions. Here, an adaptive background-corrected framework for image-based microalgae biomass estimation is proposed based on polynomial RGB regression analysis. By preserving directional information within multi-dimensional color vectors, the proposed method improves RGB-based biomass estimation consistency under varying background conditions. The framework is implemented using a low-cost wireless sensing system (<$200) integrating adjustable LED illumination, portable colorimetric sensing, and adaptive background tuning, together with three background-correction algorithms (ratio, offset, and linear). Validation using two representative microalgal species, Nannochloropsis sp. and Isochrysis galbana, under structured experimental matrices (6 hues × 6 saturations × 6 densities) achieved cross-background average accuracies of 0.94 and 0.90, respectively. The results demonstrate that adaptive background correction can effectively reduce background chromaticity interference in RGB-based biomass estimation and provide a cost-effective strategy for portable image-based microalgae biomass monitoring.